gargantua — security grade SAFE, quality 69/100

Security audit verdict: SAFE · quality 69/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by inceptyon-labs · MCP Server · ★ 78

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is gargantua safe to install? View the security audit →

About gargantua

Gargantua Gargantua is a native macOS cleaner for developers and power users. It scans common cache, build-artifact, duplicate-file, and app-remnant locations, classifies findings by risk, explains why each item is considered safe or risky, and only removes files through explicit user-controlled flows. The project is built as a Swift Package with four executables: : the SwiftUI macOS app : a local Model Context Protocol server for automation-driven scans and guarded cleanups : a launchd-driven background runner used by Scheduled Scans : an SMAppService/XPC helper for operations that require elevated trust <img src="docs/site/screenshots/readme-dashboard.png" wid

agplcleanermacosmcpmlxmodel-context-protocolswiftswiftpm

Quick Facts

Stars78
Forks6
LanguageSwift
CategoryMCP Server
LicenseAGPL-3.0
Quality Score68.8383507233058/100
Last Updated2026-10-03
Created2026-04-23
Platformsmcp
Est. Tokens~22k

gargantua alternative? Top 6 similar tools

Looking for a gargantua alternative? If you're comparing gargantua with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • HomeClaw by omarshahine · ⭐ 175

    HomeKit smart home control via MCP — lights, locks, thermostats, and scenes for Claude Desktop, Claude Code, a

  • toolhive-studio by stacklok · ⭐ 169

    ToolHive is an application that allows you to install, manage and run MCP servers and connect them to AI agent

  • SAM by SyntheticAutonomicMind · ⭐ 130

    Synthetic Autonomic Mind - An AI assistant for everyone.

  • xc-mcp by conorluddy · ⭐ 95

    XCode CLI MCP: Convenience wrapper for Xcode CLI tools & iOS Simulator. Progressive disclosure of tool respons

  • daymon by daymonio · ⭐ 365

    Daymon puts your favorite AI to work 24/7. It schedules, remembers, and orchestrates your own virtual team. Fr

  • mac_messages_mcp by carterlasalle · ⭐ 331

    An MCP server that securely interfaces with your iMessage database via the Model Context Protocol (MCP), allow

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Swift Agent Tools

Frequently Asked Questions

What is gargantua?

gargantua is Native macOS system cleaner with YAML-driven safety rules, local AI explainability via MLX, and an MCP server for agent-controlled cleanup workflows.. It is categorized as a MCP Server with 78 GitHub stars.

What programming language is gargantua written in?

gargantua is primarily written in Swift. It covers topics such as agpl, cleaner, macos.

How do I install or use gargantua?

You can find installation instructions and usage details in the gargantua GitHub repository at github.com/inceptyon-labs/gargantua. The project has 78 stars and 6 forks, indicating an active community.

What license does gargantua use?

gargantua is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to gargantua?

The top alternatives to gargantua on Agent Skills Hub include HomeClaw, toolhive-studio, SAM. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools